© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 34130
    Prev
    Next
    INDEX
    Explanations

    more Girls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ually
    -0.11
    ery
    -0.10
    angular
    -0.09
    master
    -0.09
    elier
    -0.09
    ured
    -0.09
    åĨ°æ·ĩ
    -0.08
    ÙĪع
    -0.08
     Buch
    -0.08
    uum
    -0.08
    POSITIVE LOGITS
    éĶµ
    0.10
    arty
    0.10
    çīĮ
    0.10
    çIJ¨
    0.10
    jeta
    0.09
    ÅĽ
    0.09
    æįĭ
    0.09
    ãģªãģĬ
    0.09
    -UA
    0.09
    åĪĩåħ¥çĤ¹
    0.09
    Activations Density 0.005%

    No Known Activations